My research focuses on the mathematical foundation of data science with emphasis on optimization techniques for operations research, machine learning and statistical estimations. This includes computational methods for large scale semidefinite programming, stochastic programming and modern nonconvex nondifferentiable optimization problems. I am also interested in second order variational analysis for matrix optimization problems.


  • Spring 2020: IE 3521 Statistics, Quality and Reliability.



  • Nonsmooth Composite Matrix Optimization: Strong Regularity, Constraint Nondegeneracy and Beyond.

Ying Cui and Chao Ding (2019). [link]

  • Statistical Analysis of Stationary Solutions of Coupled Nonconvex Nonsmooth Empirical Risk Minimization.

Zhengling Qi, Ying Cui, Yufeng Liu and Jong-Shi Pang (2018). [link]

  • Clustering by Orthogonal NMF Model and Non-Convex Penalty Optimization.

Shuai Wang, Tsung-Hui Chang, Ying Cui and Jong-Shi Pang (2019). [link]

  • Multi-Composite Nonconvex Optimization for Training Deep Neural Networks.

Ying Cui, Ziyu He and Jong-Shi Pang (2018). [pdf]

  • Two-Stage Stochastic Programming with Linearly Bi-Parameterized Quadratic Recourse.

Junyi Liu, Ying Cui, Jong-Shi Pang and Suvrajeet Sen (2018). [pdf]

  • A Study of Piecewise Linear-Quadratic Programs.

Ying Cui, Tsung-Hui Chang, Mingyi Hong and Jong-Shi Pang (2018).

Published papers:

  • Computing the Best Approximation Over the Intersection of a Polyhedral Set and the Doubly Nonnegative Cone.

Ying Cui, Defeng Sun and Kim-Chuan Toh.

SIAM Journal on Optimization, 29 (2019) 2785 - 2813. [link] [pdf]

  • ​Estimation of Individualized Decision Rules Based on an Optimized Covariate-dependent Equivalent of Random Outcomes.

Zhengling Qi, Ying Cui, Yufeng Liu and Jong-Shi Pang.

SIAM Journal on Optimization, 29 (2019) 2337-2362. [link] [pdf]

  • On the R-Superlinear Convergence of the KKT Residuals Generated by the Augmented Lagrangian Method for Convex Composite Conic Programming.

Ying Cui, Defeng Sun and Kim-Chuan Toh.

Mathematical Programming, Series A,178 (2019) 381-415. [link] [pdf]

  • Composite Difference-Max Programs for Modern Statistical Estimation Problems.

Ying Cui, Jong-Shi Pang and Bodhisattva Sen.

SIAM Journal on Optimization, 28 (2018) 3344-3374. [link] [pdf]

  • A Complete Characterization of the Robust Isolated Calmness of Nuclear Norm Regularized Convex Optimization Problems.

​Ying Cui and Defeng Sun.

Journal of Computational Mathematics, 36 (2018) 441-458. [link] [pdf]

  • Quadratic Growth Conditions for Convex Matrix Optimization Problems Associated with Spectral Functions.

Ying Cui, Chao Ding and Xinyuan Zhao.

SIAM Journal on Optimization, 27 (2017) 2332-2355. [link] [pdf]

  • On the Convergence Properties of a Majorized ADMM for Linearly Constrained Convex Optimization Problems with Coupled Objective Functions.

Ying Cui, Xudong Li, Defeng Sun and Kim-Chuan Toh.

Journal of Optimization Theory and Applications, 169 (2016) 1013-1041. [link] [pdf]

  • Sparse Estimation of High-dimensional Correlation Matrices.

Ying Cui, Chenlei Leng and Defeng Sun.

Computational Statistics & Data Analysis, 93 (2016) 390-403. [link] [pdf]